MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning
- Published
- Source
- arXiv
- Paper number
- 1212
- Field
- Research Agents
- arXiv ID
- 2610.19920
Key points
- The authors extracted approximately 1.6M scaffolds from the Enamine commercial molecular library and organized them into a coarse-to-fine hierarchical action space from H1 to H7.
- The agent chooses scaffold navigation, molecular editing, and undo within a single harness, while the environment maintains trajectory memory as a structured state to support long-horizon search.
- Without training, connecting Grok-4.6 to MolHop raised drug-task joint@H1 from 41.0% to 64.0% and the commercial-compound task from 36.5% to 69.0%.
- MolHop-9B, trained with SFT followed by GRPO, achieved joint@H1 of 55.5% on the drug dataset and 73.5% on the commercial dataset, beating GPT-5.6-sol, Claude-5-Opus, and Gemini-3.1-Pro.
- Candidates from MolHop-9B showed scaffold Tanimoto medians of 0.123 and 0.115, indicating larger structural differences than baseline models.
- Removing the scaffold library or trajectory memory caused substantial performance drops, confirming that the hierarchical search space and memory are key to long-horizon search.
Paper links
External research summaries. These are not HDATF publications or measured product results.